This is on embedded, but I have seen the same note about STDIO and prinf also for realtime on big platforms (somewhere, as usual):
http://ez.analog.com/docs/DOC-1988 so yes maybe it is time to carefully look in the messaging on the PREEMPT_RT port. j. On Sat, May 5, 2012 at 12:20 PM, Jan de Kruyf <jan.de.kr...@gmail.com>wrote: > fom here: > > https://rt.wiki.kernel.org/index.php/HOWTO:_Build_an_RT-application > > ------------------------------------------ > A real-time system *cannot* be real-time if there is no solution for priority > inversion <https://rt.wiki.kernel.org/index.php/Priority_inversion>, this > will cause undesired latencies and even deadlocks. (see > [2]<http://en.wikipedia.org/wiki/Priority_inversion>) > > On Linux luckily there is a solution for it in user-land since kernel > version 2.6.18 together with Glibc 2.5 (PTHREAD_PRIO_INHERIT). > So, if user-land real-time is important, I highly encourage you to use a > recent kernel and Glibc-library. Other C-libraries like uClibc do not > support PI-futexes at this moment, and are therefore less suitable for > realtime! > ---------------------------------------------- > > So I did find it. And I switched to this thread. > > > j. > > > > > On Sat, May 5, 2012 at 5:19 AM, Charles Steinkuehler < > char...@steinkuehler.net> wrote: > >> On 5/4/2012 10:08 PM, John Morris wrote: >> > I suppose that 2x-4x the original setting might possibly be enough, >> > probably don't need 256x. I'll wait to see if the list suggests any >> > heuristics for picking a good number. >> >> The two main approaches I've seen used are to either rigorously prove >> the maximum stack size by analyzing the code (complex and generally not >> worth the hassle unless lives are at stake), or by filling the stack >> region with known values, running the code, seeing how much stack >> _actually_ got used, and adding a fudge factor. >> >> There are many other ways to tweak stack size, but since I doubt there >> is a strong need to minimize memory usage, adding a fudge factor (even >> 2x or 4x or more expected usage) seems reasonable. >> >> -- >> Charles Steinkuehler >> char...@steinkuehler.net >> >> >> ------------------------------------------------------------------------------ >> Live Security Virtual Conference >> Exclusive live event will cover all the ways today's security and >> threat landscape has changed and how IT managers can respond. Discussions >> will include endpoint security, mobile security and the latest in malware >> threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ >> _______________________________________________ >> Emc-developers mailing list >> Emc-developers@lists.sourceforge.net >> https://lists.sourceforge.net/lists/listinfo/emc-developers >> > > ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ _______________________________________________ Emc-developers mailing list Emc-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-developers
